Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A Medium post in the "AI in Plain English" series argues that BM25 keyword ranking remains essential to retrieval-augmented generation (RAG) systems even as embeddings draw widespread attention. The author walks through …
InclusionAI released Ling-3.0-flash-VL, a hybrid instant/reasoning model with tool calling that builds on Ling 3.0 Flash (124B total / 5.5B active MoE) and adds native visual perception and advanced visual agent capabili…
Quixotic AI released jinfer, an early CPU-only inference engine for the JVM that supports chat, vision, audio, embeddings, reranking, and TTS without a Python runtime, ONNX, Docker containers, sidecar processes, or IPC. …
A practical guide for founders and product teams outlines how to build production-ready custom AI agents in 2026, covering architecture, orchestration, tools, retrieval-augmented generation, memory, and guardrails. It ad…
A developer's cost breakdown argues that teams should default to retrieval-augmented generation when a model lacks business knowledge and to prompt engineering when it answers in the wrong style, reserving fine-tuning fo…
Researchers Xianming Li, Zongxi Li and Tsz-fung Andrew Lee merged ShadowPEFT into the main branch of Hugging Face's PEFT library, adding a stateful shadow network that can be detached with unload_shadow() and run as a sm…
OpenAI researcher Daniel Selsam, who has worked on model training at the company for almost five years, publicly stated on Monday that he is "extremely concerned" about how far AI models have come and that "merely pacing…
A developer surveyed six AI memory systems — Cognee, Mem0, Letta, Supermemory, Zep, and Mnemoverse — to determine whether any publish an input that accepts an explicitly negative verdict on a recalled memory and changes …
Microsoft's Foundry Local lets developers embed AI inference directly inside application binaries, using the same SDK and API shapes as the company's cloud Foundry offerings, with automatic hardware acceleration and no b…
Bill Gates warned that no government is prepared for the societal upheaval artificial intelligence will cause, saying he has lobbied world leaders including President Donald Trump and plans to meet China's President Xi J…
Neurogrid launched a community cloud that connects owners of underutilized GPUs with users who need affordable AI inference, letting GPU providers earn from workloads run on their idle hardware. The marketplace routes co…
Capybala released a SKILL.md workflow that drives headless Blender through a Stage A → B → C process — planning the component list, building against calibrated camera, lighting, and material presets, then self-reviewing …
A developer tested CrewAI 1.15.21 with three agents — an Analyst and Writer on Qwen 3 235B via OpenRouter and an Editor on Anthropic's Claude Opus 4.8 — and found that apparent agent-to-agent conversation is actually too…
GoTo, the Indonesian technology group and parent company of Gojek, is narrowing its AI investments to applications that improve customer conversion or cut costs, ahead of a wider rollout in 2027, president director and g…
A new research paper proposes learning to select poison sets rather than sampling them at random, aiming to strengthen backdoor poisoning attacks on large language models. Backdoor poisoning attacks add poisoned examples…
LangSmith, a monitoring and observability platform built by the creators of LangChain and LangGraph, traces AI applications by logging every input and output across each step of a pipeline, according to a technical deep …
A study comparing traditional machine learning models against LLM-generated rule-based systems for heart disease prediction on the UCI Heart Disease dataset found that traditional models consistently outperformed the LLM…
A new arXiv paper (2609.13201v1) models AI-generated text and images as anomalies linked to main data points and derives bounds on the minimum size of a strongly dissimilar decomposition of random datasets using redundan…
A controlled study across several versions of two major tabular foundation model (TFM) families found that feature engineering gains are concentrated in earlier model generations and become negligible for the strongest m…
A new analysis method called Elo-per-token measures how large language model agents allocate test-time compute as they revise solutions, use tools, explore alternatives, and decide when to stop, addressing the difficulty…